Daejeon, South Korea
I am a third-year Ph.D. candidate at KAIST and doing an internship at Huawei in London . My research focuses on Video Large Language Models, with a particular interest in improving video understanding while making inference faster and more efficient. My prior work has focused on scene understanding in the image/video domains—addressing challenges such as long-tailed distributions and data scarcity—as well as recommender systems. For more information, you can visit the following link: https://rlqja1107.github.io/
Host: Zhensong Zhang Internship at Huawei Noah’s Ark Lab
Host: Prof. Julian McAuley Projects: 1. [ICLR'26] Token-Efficient Item Representation via Images for LLM Recommender Systems. 2. [Under Review at ECCV'26] Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs